Computer-based image analysis in breast pathology

Semi-automated analysis of HER2 immunohistochemistry in invasive breast carcinoma using whole slide images: utility for interpretation in clinical practice

Human epidermal growth factor receptor 2 (HER2) gene amplification and subsequent protein overexpression is a strong prognostic and predictive biomarker in invasive breast carcinoma (IBC). ASCO/CAP recommended tests for HER2 assessment include immunohistochemistry (IHC) and/or in situ hybridization (ISH). Accurate HER2 IHC scoring (0, 1+, 2+, 3+) is key for appropriate classification and treatment of IBC. HER2-targeted therapies, including anti-HER2 monoclonal antibodies and antibody drug conjugates (ADC), have revolutionized the treatment of HER2-positive IBC. Recently, ADC have also been approved for treatment of HER2-low (IHC 1+, IHC 2+/ISH-) advanced breast carcinoma, making a distinction between IHC 0 and 1+ crucial. In this focused study, 32 IBC with HER2 IHC scores from 0 to 3+ and HER2 FISH results formed a calibration dataset, and 77 IBC with HER2 IHC score 2+ and paired FISH results (27 amplified, 50 non-amplified) formed a validation dataset. H&E and HER2 IHC whole slide images (WSI) were scanned. Regions of interest were manually annotated and IHC scores generated by the software QuantCenter (MembraneQuant application) by 3DHISTECH Ltd. (Budapest, Hungary) and compared to the microscopic IHC score. H-scores [(3×%IHC3+) +(2×%IHC2+) +(1×%IHC1+)] were calculated for semi-automated (MembraneQuant) analysis. Concordance between microscopic IHC scoring and 3DHISTECH MembraneQuant semi-automated scoring in the calibration dataset showed a Kappa value of 0.77 (standard error 0.09). Microscopic IHC and MembraneQuant image analysis for the detection of HER2 amplification yielded a sensitivity of 100% for both and a specificity of 56% and 61%, respectively. In the validation set of IHC 2+ cases, only 13 of 77 cases (17%) had discordant results between microscopic and MembraneQuant images, and various artifacts limiting the interpretation of HER2 IHC, including cytoplasmic/granular staining and crush artifact were noted. Semi-automated analysis using WSI and microscopic evaluation yielded similar HER2 IHC scores, demonstrating the potential utility of this tool for interpretation in clinical practice and subsequent accurate treatment. In this study, it was shown that semi-automatic HER2 IHC interpretation provides an objective approach to a test known to be quite subjective.

Revolutionizing Pathology with Artificial Intelligence: Innovations in Immunohistochemistry

Artificial intelligence (AI) is a reality of our times, and it has been successfully implemented in all fields, including medicine. As a relatively new domain, all efforts are directed towards creating algorithms applicable in most medical specialties. Pathology, as one of the most important areas of interest for precision medicine, has received significant attention in the development and implementation of AI algorithms. This focus is especially important for achieving accurate diagnoses. Moreover, immunohistochemistry (IHC) serves as a complementary diagnostic tool in pathology. It can be further augmented through the application of deep learning (DL) and machine learning (ML) algorithms for assessing and analyzing immunohistochemical markers. Such advancements can aid in delineating targeted therapeutic approaches and prognostic stratification. This article explores the applications and integration of various AI software programs and platforms used in immunohistochemical analysis. It concludes by highlighting the application of these technologies to pathologies such as breast, prostate, lung, melanocytic proliferations, and hematologic conditions. Additionally, it underscores the necessity for further innovative diagnostic algorithms to assist physicians in the diagnostic process.

Augmented interpretation of HER2, ER, and PR in breast cancer by artificial intelligence analyzer: enhancing interobserver agreement through a reader study of 201 cases

BACKGROUND

Accurate classification of breast cancer molecular subtypes is crucial in determining treatment strategies and predicting clinical outcomes. This classification largely depends on the assessment of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), and progesterone receptor (PR) status. However, variability in interpretation among pathologists pose challenges to the accuracy of this classification. This study evaluates the role of artificial intelligence (AI) in enhancing the consistency of these evaluations.

METHODS

AI-powered HER2 and ER/PR analyzers, consisting of cell and tissue models, were developed using 1,259 HER2, 744 ER, and 466 PR-stained immunohistochemistry (IHC) whole-slide images of breast cancer. External validation cohort comprising HER2, ER, and PR IHCs of 201 breast cancer cases were analyzed with these AI-powered analyzers. Three board-certified pathologists independently assessed these cases without AI annotation. Then, cases with differing interpretations between pathologists and the AI analyzer were revisited with AI assistance, focusing on evaluating the influence of AI assistance on the concordance among pathologists during the revised evaluation compared to the initial assessment.

RESULTS

Reevaluation was required in 61 (30.3%), 42 (20.9%), and 80 (39.8%) of HER2, in 15 (7.5%), 17 (8.5%), and 11 (5.5%) of ER, and in 26 (12.9%), 24 (11.9%), and 28 (13.9%) of PR evaluations by the pathologists, respectively. Compared to initial interpretations, the assistance of AI led to a notable increase in the agreement among three pathologists on the status of HER2 (from 49.3 to 74.1%, p < 0.001), ER (from 93.0 to 96.5%, p = 0.096), and PR (from 84.6 to 91.5%, p = 0.006). This improvement was especially evident in cases of HER2 2+ and 1+, where the concordance significantly increased from 46.2 to 68.4% and from 26.5 to 70.7%, respectively. Consequently, a refinement in the classification of breast cancer molecular subtypes (from 58.2 to 78.6%, p < 0.001) was achieved with AI assistance.

CONCLUSIONS

This study underscores the significant role of AI analyzers in improving pathologists' concordance in the classification of breast cancer molecular subtypes.

An interpretable decision-support model for breast cancer diagnosis using histopathology images

Microscopic examination of biopsy tissue slides is perceived as the gold-standard methodology for the confirmation of presence of cancer cells. Manual analysis of an overwhelming inflow of tissue slides is highly susceptible to misreading of tissue slides by pathologists. A computerized framework for histopathology image analysis is conceived as a diagnostic tool that greatly benefits pathologists, augmenting definitive diagnosis of cancer. Convolutional Neural Network (CNN) turned out to be the most adaptable and effective technique in the detection of abnormal pathologic histology. Despite their high sensitivity and predictive power, clinical translation is constrained by a lack of intelligible insights into the prediction. A computer-aided system that can offer a definitive diagnosis and interpretability is therefore highly desirable. Conventional visual explanatory techniques, Class Activation Mapping (CAM), combined with CNN models offers interpretable decision making. The major challenge in CAM is, it cannot be optimized to create the best visualization map. CAM also decreases the performance of the CNN models. To address this challenge, we introduce a novel interpretable decision-support model using CNN with a trainable attention mechanism using response-based feed-forward visual explanation. We introduce a variant of DarkNet19 CNN model for the classification of histopathology images. In order to achieve visual interpretation as well as boost the performance of the DarkNet19 model, an attention branch is integrated with DarkNet19 network forming Attention Branch Network (ABN). The attention branch uses a convolution layer of DarkNet19 and Global Average Pooling (GAP) to model the context of the visual features and generate a heatmap to identify the region of interest. Finally, the perception branch is constituted using a fully connected layer to classify images. We trained and validated our model using more than 7000 breast cancer biopsy slide images from an openly available dataset and achieved 98.7% accuracy in the binary classification of histopathology images. The observations substantiated the enhanced clinical interpretability of the DarkNet19 CNN model, supervened by the attention branch, besides delivering a 3%-4% performance boost of the baseline model. The cancer regions highlighted by the proposed model correlate well with the findings of an expert pathologist. The coalesced approach of unifying attention branch with the CNN model capacitates pathologists with augmented diagnostic interpretability of histological images with no detriment to state-of-art performance. The model's proficiency in pinpointing the region of interest is an added bonus that can lead to accurate clinical translation of deep learning models that underscore clinical decision support.

Weakly-Supervised Classification of HER2 Expression in Breast Cancer Haematoxylin and Eosin Stained Slides

Human epidermal growth factor receptor 2 (HER2) evaluation commonly requires immunohistochemistry (IHC) tests on breast cancer tissue, in addition to the standard haematoxylin and eosin (H&E) staining tests. Additional costs and time spent on further testing might be avoided if HER2 overexpression could be effectively inferred from H&E stained slides, as a preliminary indication of the IHC result. In this paper, we propose the first method that aims to achieve this goal. The proposed method is based on multiple instance learning (MIL), using a convolutional neural network (CNN) that separately processes H&E stained slide tiles and outputs an IHC label. This CNN is pretrained on IHC stained slide tiles but does not use these data during inference/testing. H&E tiles are extracted from invasive tumour areas segmented with the HASHI algorithm. The individual tile labels are then combined to obtain a single label for the whole slide. The network was trained on slides from the HER2 Scoring Contest dataset (HER2SC) and tested on two disjoint subsets of slides from the HER2SC database and the TCGA-TCIA-BRCA (BRCA) collection. The proposed method attained 83.3 % classification accuracy on the HER2SC test set and 53.8 % on the BRCA test set. Although further efforts should be devoted to achieving improved performance, the obtained results are promising, suggesting that it is possible to perform HER2 overexpression classification on H&E stained tissue slides.

Review of the current state of digital image analysis in breast pathology

Advances in digital image analysis have the potential to transform the practice of breast pathology. In the near future, a move to a digital workflow offers improvements in efficiency. Coupled with artificial intelligence (AI), digital pathology can assist pathologist interpretation, automate time-consuming tasks, and discover novel morphologic patterns. Opportunities for digital enhancements abound in breast pathology, from increasing reproducibility in grading and biomarker interpretation, to discovering features that correlate with patient outcome and treatment. Our objective is to review the most recent developments in digital pathology with clear impact to breast pathology practice. Although breast pathologists currently undertake limited adoption of digital methods, the field is rapidly evolving. Care is needed to validate emerging technologies for effective patient care.

Machine Learning Methods for Computer-Aided Breast Cancer Diagnosis Using Histopathology: A Narrative Review

Histopathology is a method used for breast cancer diagnosis. Machine learning (ML) methods have achieved success for supervised learning tasks in the medical domain. In this article, we investigate the impact of ML for the diagnosis of breast cancer using histopathology images of conventional photomicroscopy. Cancer diagnosis is the identification of images as cancer or noncancer, and this involves image preprocessing, feature extraction, classification, and performance analysis. In this article, different approaches to perform these necessary steps are reviewed. We find that most ML research for breast cancer diagnosis has been focused on deep learning. Based on inferences from the recent research activities, we discuss how ML methods can benefit conventional microscopy-based breast cancer diagnosis. Finally, we discuss the research gaps of ML approaches for the implementation in a real pathology environment and propose future research guidelines.

The Immune Response in Nonmetastatic Axillary Lymph Nodes Is Associated with the Presence of Axillary Metastasis and Breast Cancer Patient Outcome

Tumor cells can modify the immune response in primary tumors and in the axillary lymph nodes with metastasis (ALN⁺) in breast cancer (BC), influencing patient outcome. We investigated whether patterns of immune cells in the primary tumor and in the axillary lymph nodes without metastasis (ALN^-) differed between patients diagnosed without ALN⁺ (diagnosed-ALN^-) and with ALN⁺ (diagnosed-ALN⁺) and the implications for clinical outcome. Eleven immune markers were studied using immunohistochemistry, tissue microarray, and digital image analysis in 141 BC patient samples (75 diagnosed-ALN⁺ and 66 diagnosed-ALN^-). Two logistic regression models were derived to identify the clinical, pathologic, and immunologic variables associated with the presence of ALN⁺ at diagnosis. There are immune patterns in the ALN^- associated with the presence of ALN⁺ at diagnosis. The regression models revealed a small subgroup of diagnosed-ALN⁺ with ALN^- immune patterns that were more similar to those of the ALN^- of the diagnosed-ALN^-. This small subgroup also showed similar clinical behavior to that of the diagnosed-ALN^-. Another small subgroup of diagnosed-ALN^- with ALN^- immune patterns was found whose members were more similar to those of the ALN^- of the diagnosed-ALN⁺. This small subgroup had similar clinical behavior to the diagnosed-ALN⁺. These data suggest that the immune response present in ALN^- at diagnosis could influence the clinical outcome of BC patients.

Using Digital Pathology to Understand Epithelial Characteristics of Benign Breast Disease among Women Undergoing Diagnostic Image-Guided Breast Biopsy

Delayed terminal duct lobular unit (TDLU) involution is associated with elevated mammographic breast density (MD). Both are independent breast cancer risk factors among women with benign breast disease (BBD). Prior digital analyses of normal breast tissues revealed that epithelial nuclear density (END) and TDLU involution are inversely correlated. Accordingly, we examined associations of END, TDLU involution, and MD in BBD clinical biopsies. This study included digitized images of 262 representative image-guided hematoxylin and eosin-stained biopsies from 224 women diagnosed with BBD, enrolled within the cross-sectional BREAST-Stamp project that were visually assessed for TDLU involution (TDLU count/100 mm², median TDLU span and median acini count per TDLU). A digital algorithm estimated nuclei count per unit epithelial area, or END. Single X-ray absorptiometry of prebiopsy ipsilateral craniocaudal digital mammograms measured global and localized MD surrounding the biopsy region. Adjusted ordinal logistic regression models assessed relationships between tertiles of TDLU and END measures. Analysis of covariance examined mean differences in MD across END tertiles. TDLU measures were positively associated with increasing END tertiles [TDLU count/100 mm², OR_T3vsT1: 3.42, 95% confidence interval (CI), 1.87-6.28; acini count/TDLU_T3vsT1, OR: 2.40, 95% CI, 1.39-4.15]. END was significantly associated with localized, but not, global MD. Relationships were most apparent among patients with nonproliferative BBD. These findings suggest that quantitative END reflects different but complementary information to the histologic information captured by visual TDLU and radiologic MD measures and merits continued evaluation in assessing cellularity of breast parenchyma to understand the etiology of BBD.

Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study

Inter-pathologist agreement for nuclear atypia scoring of breast cancer is poor. To address this problem, previous studies suggested some criteria for describing the variations appearance of tumor cells relative to normal cells. However, these criteria were still assessed subjectively by pathologists. Previous studies used quantitative computer-extracted features for scoring. However, application of these tools is limited as further improvement in their accuracy is required. This study proposes COMPASS (COMputer-assisted analysis combined with Pathologist's ASSessment) for reproducible nuclear atypia scoring. COMPASS relies on both cytological criteria assessed subjectively by pathologists as well as computer-extracted textural features. Using machine learning, COMPASS combines these two sets of features and output nuclear atypia score. COMPASS's performance was evaluated using 300 images for which expert-consensus derived reference nuclear pleomorphism scores were available, and they were scanned by two scanners from different vendors. A personalized model was built for three pathologists who gave scores to six atypia-related criteria for each image. Leave-one-out cross validation (LOOCV) was used. COMPASS was trained and tested for each pathologist separately. Percentage agreement between COMPASS and the reference nuclear scores was 93.8%, 92.9%, and 93.1% for three pathologists. COMPASS's performance in nuclear grading was almost identical for both scanners, with Cohen's kappa ranging from 0.80 to 0.86 for different pathologists and different scanners. Independently, the images were also assessed by two experienced senior pathologists. Cohen's kappa of COMPASS was comparable to the Cohen's kappa for two senior pathologists (0.79 and 0.68).

Recognizing basal cell carcinoma on smartphone-captured digital histopathology images with a deep neural network

BACKGROUND

Pioneering effort has been made to facilitate the recognition of pathology in malignancies based on whole-slide images (WSIs) through deep learning approaches. It remains unclear whether we can accurately detect and locate basal cell carcinoma (BCC) using smartphone-captured images.

OBJECTIVES

To develop deep neural network frameworks for accurate BCC recognition and segmentation based on smartphone-captured microscopic ocular images (MOIs).

METHODS

We collected a total of 8046 MOIs, 6610 of which had binary classification labels and the other 1436 had pixelwise annotations. Meanwhile, 128 WSIs were collected for comparison. Two deep learning frameworks were created. The 'cascade' framework had a classification model for identifying hard cases (images with low prediction confidence) and a segmentation model for further in-depth analysis of the hard cases. The 'segmentation' framework directly segmented and classified all images. Sensitivity, specificity and area under the curve (AUC) were used to evaluate the overall performance of BCC recognition.

RESULTS

The MOI- and WSI-based models achieved comparable AUCs around 0·95. The 'cascade' framework achieved 0·93 sensitivity and 0·91 specificity. The 'segmentation' framework was more accurate but required more computational resources, achieving 0·97 sensitivity, 0·94 specificity and 0·987 AUC. The runtime of the 'segmentation' framework was 15·3 ± 3·9 s per image, whereas the 'cascade' framework took 4·1 ± 1·4 s. Additionally, the 'segmentation' framework achieved 0·863 mean intersection over union.

CONCLUSIONS

Based on the accessible MOIs via smartphone photography, we developed two deep learning frameworks for recognizing BCC pathology with high sensitivity and specificity. This work opens a new avenue for automatic BCC diagnosis in different clinical scenarios. What's already known about this topic? The diagnosis of basal cell carcinoma (BCC) is labour intensive due to the large number of images to be examined, especially when consecutive slide reading is needed in Mohs surgery. Deep learning approaches have demonstrated promising results on pathological image-related diagnostic tasks. Previous studies have focused on whole-slide images (WSIs) and leveraged classification on image patches for detecting and localizing breast cancer metastases. What does this study add? Instead of WSIs, microscopic ocular images (MOIs) photographed from microscope eyepieces using smartphone cameras were used to develop neural network models for recognizing BCC automatically. The MOI- and WSI-based models achieved comparable areas under the curve around 0·95. Two deep learning frameworks for recognizing BCC pathology were developed with high sensitivity and specificity. Recognizing BCC through a smartphone could be considered a future clinical choice.

A deep learning algorithm for one-step contour aware nuclei segmentation of histopathology images

This paper addresses the task of nuclei segmentation in high-resolution histopathology images. We propose an automatic end-to-end deep neural network algorithm for segmentation of individual nuclei. A nucleus-boundary model is introduced to predict nuclei and their boundaries simultaneously using a fully convolutional neural network. Given a color-normalized image, the model directly outputs an estimated nuclei map and a boundary map. A simple, fast, and parameter-free post-processing procedure is performed on the estimated nuclei map to produce the final segmented nuclei. An overlapped patch extraction and assembling method is also designed for seamless prediction of nuclei in large whole-slide images. We also show the effectiveness of data augmentation methods for nuclei segmentation task. Our experiments showed our method outperforms prior state-of-the-art methods. Moreover, it is efficient that one 1000×1000 image can be segmented in less than 5 s. This makes it possible to precisely segment the whole-slide image in acceptable time. The source code is available at https://github.com/easycui/nuclei_segmentation . Graphical Abstract The neural network for nuclei segmentation.

Deep Learning in the Biomedical Applications: Recent and Future Status

Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.

Analysis of Image Feature Characteristics for Automated Scoring of HER2 in Histology Slides

The evaluation of breast cancer grades in immunohistochemistry (IHC) slides takes into account various types of visual markers and morphological features of stained membrane regions. Digital pathology algorithms using whole slide images (WSIs) of histology slides have recently been finding several applications in such computer-assisted evaluations. Features that are directly related to biomarkers used by pathologists are generally preferred over the pixel values of entire images, even though the latter has more information content. This paper explores in detail various types of feature measurements that are suitable for the automated scoring of human epidermal growth factor receptor 2 (HER2) in histology slides. These are intensity features known as characteristic curves, texture features in the form of uniform local binary patterns (ULBPs), morphological features specifying connectivity of regions, and first-order statistical features of the overall intensity distribution. This paper considers important properties of the above features and outlines methods for reducing information redundancy, maximizing inter-class separability, and improving classification accuracy in the combined feature set. This paper also presents a detailed experimental analysis performed using the aforementioned features on a WSI dataset of IHC stained slides.

Quantitative Characterization of CD8+ T Cell Clustering and Spatial Heterogeneity in Solid Tumors

Quantitative characterization of the tumor microenvironment, including its immuno-architecture, is important for developing quantitative diagnostic and predictive biomarkers, matching patients to the most appropriate treatments for precision medicine, and for providing quantitative data for building systems biology computational models able to predict tumor dynamics in the context of immune checkpoint blockade therapies. The intra- and inter-tumoral spatial heterogeneities are potentially key to the understanding of the dose-response relationships, but they also bring challenges to properly parameterizing and validating such models. In this study, we developed a workflow to detect CD8+ T cells from whole slide imaging data, and quantify the spatial heterogeneity using multiple metrics by applying spatial point pattern analysis and morphometric analysis. The results indicate a higher intra-tumoral heterogeneity compared with the heterogeneity across patients. By comparing the baseline metrics with PD-1 blockade treatment outcome, our results indicate that the number of high-density T cell clusters of both circular and elongated shapes are higher in patients who responded to the treatment. This methodology can be applied to quantitatively characterize the tumor microenvironment, including immuno-architecture, and its heterogeneity for different cancer types.

Digital pathology: semper ad meliora

This review is an evidence-based summary of digital pathology: past, present and future. It discusses digital surgical pathology and the cytopathology digitisation challenge as well as the performance of digital histopathology and cytopathology as a diagnostic tool, particularly in contrast to user perceptions. Time and cost efficiency of digital pathology, learning curves, education and quality assurance, with the importance of validation of systems, is emphasised. The review concludes with a discussion of digital pathology as a source of 'big data' and where this might lead pathologists in the digital pathology future.

Automatic cellularity assessment from post-treated breast surgical specimens

Neoadjuvant treatment (NAT) of breast cancer (BCa) is an option for patients with the locally advanced disease. It has been compared with standard adjuvant therapy with the aim of improving prognosis and surgical outcome. Moreover, the response of the tumor to the therapy provides useful information for patient management. The pathological examination of the tissue sections after surgery is the gold-standard to estimate the residual tumor and the assessment of cellularity is an important component of tumor burden assessment. In the current clinical practice, tumor cellularity is manually estimated by pathologists on hematoxylin and eosin (H&E) stained slides, the quality, and reliability of which might be impaired by inter-observer variability which potentially affects prognostic power assessment in NAT trials. This procedure is also qualitative and time-consuming. In this paper, we describe a method of automatically assessing cellularity. A pipeline to automatically segment nuclei figures and estimate residual cancer cellularity from within patches and whole slide images (WSIs) of BCa was developed. We have compared the performance of our proposed pipeline in estimating residual cancer cellularity with that of two expert pathologists. We found an intra-class agreement coefficient (ICC) of 0.89 (95% CI of [0.70, 0.95]) between pathologists, 0.74 (95% CI of [0.70, 0.77]) between pathologist #1 and proposed method, and 0.75 (95% CI of [0.71, 0.79]) between pathologist #2 and proposed method. We have also successfully applied our proposed technique on a WSI to locate areas with high concentration of residual cancer. The main advantage of our approach is that it is fully automatic and can be used to find areas with high cellularity in WSIs. This provides a first step in developing an automatic technique for post-NAT tumor response assessment from pathology slides. © 2017 International Society for Advancement of Cytometry.

Determining Image Processing Features Describing the Appearance of Challenging Mitotic Figures and Miscounted Nonmitotic Objects

Context:

Previous studies showed that the agreement among pathologists in recognition of mitoses in breast slides is fairly modest.

Aims:

Determining the significantly different quantitative features among easily identifiable mitoses, challenging mitoses, and miscounted nonmitoses within breast slides and identifying which color spaces capture the difference among groups better than others.

Materials and Methods:

The dataset contained 453 mitoses and 265 miscounted objects in breast slides. The mitoses were grouped into three categories based on the confidence degree of three pathologists who annotated them. The mitoses annotated as “probably a mitosis” by the majority of pathologists were considered as the challenging category. The miscounted objects were recognized as a mitosis or probably a mitosis by only one of the pathologists. The mitoses were segmented using k-means clustering, followed by morphological operations. Morphological, intensity-based, and textural features were extracted from the segmented area and also the image patch of 63 × 63 pixels in different channels of eight color spaces. Holistic features describing the mitoses' surrounding cells of each image were also extracted.

Statistical Analysis Used:

The Kruskal–Wallis H-test followed by the Tukey-Kramer test was used to identify significantly different features.

Results:

The results indicated that challenging mitoses were smaller and rounder compared to other mitoses. Among different features, the Gabor textural features differed more than others between challenging mitoses and the easily identifiable ones. Sizes of the non-mitoses were similar to easily identifiable mitoses, but nonmitoses were rounder. The intensity-based features from chromatin channels were the most discriminative features between the easily identifiable mitoses and the miscounted objects.

Conclusions:

Quantitative features can be used to describe the characteristics of challenging mitoses and miscounted nonmitotic objects.